B0355
Title: Latent Ornstein-Uhlenbeck models for Bayesian analysis of multivariate longitudinal categorical responses
Authors: Trung Dung Tran - Maastricht University (Netherlands) [presenting]
Abstract: To explore the association of oral health with general health information obtained from a registry done on the elderly population in Belgium, a Bayesian latent vector autoregressive (LVAR) model is proposed. This model handles multivariate balanced longitudinal data of binary and ordinal variables items as a function of a small number of continuous latent variables. The focus is on the evolution of the latent variables while taking into account the correlation structure of the responses. Often local independence is assumed in this context. Local independence implies that, given the latent variables, the responses are assumed mutually independent cross-sectionally and longitudinally. However, in practice conditioning on the latent variables may not remove the dependence of the responses. Local dependence is addressed by further conditioning on item-specific random effects. Secondly, the previous model is extended to the unbalanced case. This model is then generalized to analyse multivariate unbalanced longitudinal data. It is shown that simply assuming real eigenvalues for the drift matrix of the OU process, as is frequently done in practice, can lead to biased estimates and/or misleading inferences. In contrast, the proposal allows for both real and complex eigenvalues. The proposed model is illustrated with a motivating dataset, containing patients with amyotrophic lateral sclerosis disease. The interest is in how bulbar, cervical, and lumbar functions evolve over time.
